Search

Deep neural networks have recently been used to edit images with great success, in particular for faces. However, they are often limited to only being able to work at a restricted range of resolutions. Many methods are so flexible that face edits can often result in an unwanted loss of identity. This work proposes to learn how to perform semantic image edits through the application of smooth warp fields. Previous approaches that attempted to use warping for semantic edits required paired data, i.e. example images of the same subject with different semantic attributes. In contrast, we employ recent advances in Generative Adversarial Networks that allow our model to be trained with unpaired data. We demonstrate face editing at very high resolutions (4k images) with a single forward pass of a deep network at a lower resolution. We also show that our edits are substantially better at preserving the subject's identity. The robustness of our approach is demonstrated by showing plausible image editing results on the Cub200 birds dataset. To our knowledge this has not been previously accomplished, due the challenging nature of the dataset., CVPR 2020

This paper is the first work to propose a network to predict a structured uncertainty distribution for a synthesized image. Previous approaches have been mostly limited to predicting diagonal covariance matrices. Our novel model learns to predict a full Gaussian covariance matrix for each reconstruction, which permits efficient sampling and likelihood evaluation. We demonstrate that our model can accurately reconstruct ground truth correlated residual distributions for synthetic datasets and generate plausible high frequency samples for real face images. We also illustrate the use of these predicted covariances for structure preserving image denoising., CVPR 2018 (final version)

Variational Autoencoders (VAE) learn a latent representation of image data that allows natural image generation and manipulation. However, they struggle to generate sharp images. To address this problem, we propose a hierarchy of VAEs analogous to a Laplacian pyramid. Each network models a single pyramid level, and is conditioned on the coarser levels. The Laplacian architecture allows for novel image editing applications that take advantage of the coarse to fine structure of the model. Our method achieves lower reconstruction error in terms of MSE, which is the loss function of the VAE and is not directly minimised in our model. Furthermore, the reconstructions generated by the proposed model are preferred over those from the VAE by human evaluators.

While data has certainly taken the center stage in computer vision in recent years, it can still be difficult to obtain in certain scenarios. In particular, acquiring ground truth 3D shapes of objects pictured in 2D images remains a challenging feat and this has hampered progress in recognition-based object reconstruction from a single image. Here we propose to bypass previous solutions such as 3D scanning or manual design, that scale poorly, and instead populate object category detection datasets semi-automatically with dense, per-object 3D reconstructions, bootstrapped from:(i) class labels, (ii) ground truth figure-ground segmentations and (iii) a small set of keypoint annotations. Our proposed algorithm first estimates camera viewpoint using rigid structure-from-motion and then reconstructs object shapes by optimizing over visual hull proposals guided by loose within-class shape similarity assumptions. The visual hull sampling process attempts to intersect an object's projection cone with the cones of minimal subsets of other similar objects among those pictured from certain vantage points. We show that our method is able to produce convincing per-object 3D reconstructions and to accurately estimate cameras viewpoints on one of the most challenging existing object-category detection datasets, PASCAL VOC. We hope that our results will re-stimulate interest on joint object recognition and 3D reconstruction from a single image.

We address the problem of populating object category detection datasets with dense, per-object 3D reconstructions, bootstrapped from class labels, ground truth figure-ground segmentations and a small set of keypoint annotations. Our proposed algorithm first estimates camera viewpoint using rigid structure-from-motion, then reconstructs object shapes by optimizing over visual hull proposals guided by loose within-class shape similarity assumptions. The visual hull sampling process attempts to intersect an object's projection cone with the cones of minimal subsets of other similar objects among those pictured from certain vantage points. We show that our method is able to produce convincing per-object 3D reconstructions on one of the most challenging existing object-category detection datasets, PASCAL VOC. Our results may re-stimulate once popular geometry-oriented model-based recognition approaches.

Reconstructing the shape of a deformable object from a single image is a challenging problem, even when a 3D template shape is available. Many different methods have been proposed for this problem, however what they have in common is that they are only able to reconstruct the part of the surface which is visible in a reference image. In contrast, we are interested in recovering the full shape of a deformable 3D object. We introduce a new method designed to reconstruct closed surfaces. This type of surface is better suited for representing objects with volume. Our method relies on recent advances in silhouette Based reconstruction methods to obtain the template from a reference image. This template is then deformed in order to fit the measurements of a new input image. We combine an inextensibility prior on the deformation with powerful image measurements, in the form of silhouette and area constraints, to make our method less reliant on point correspondences. We show reconstruction results for different object classes, such as animals or hands, that have not been previously attempted with existing template methods.

Cosegmentation is typically defined as the task of jointly segmenting “something similar” in a given set of images. Existing methods are too generic and so far have not demonstrated competitive results for any specific task. In this paper we overcome this limitation by adding two new aspects to cosegmentation: (1) the “something” has to be an object, and (2) the “similarity” measure is learned. In this way, we are able to achieve excellent results on the recently introduced iCoseg dataset, which contains small sets of images of either the same object instance or similar objects of the same class. The challenge of this dataset lies in the extreme changes in viewpoint, lighting, and object deformations within each set. We are able to considerably outperform several competitors. To achieve this performance, we borrow recent ideas from object recognition: the use of powerful features extracted from a pool of candidate object-like segmentations. We believe that our work will be beneficial to several application areas, such as image retrieval.

The problem of cosegmentation consists of segmenting the same object (or objects of the same class) in two or more distinct images. Recently a number of different models have been proposed for this problem. However, no comparison of such models and corresponding optimization techniques has been done so far. We analyze three existing models: the L1 norm model of Rother et al. [1], the L2 norm model of Mukherjee et al. [2] and the "reward" model of Hochbaum and Singh [3]. We also study a new model, which is a straightforward extension of the Boykov-Jolly model for single image segmentation [4]. In terms of optimization, we use a Dual Decomposition (DD) technique in addition to optimization methods in [1,2]. Experiments show a significant improvement of DD over published methods. Our main conclusion, however, is that the new model is the best overall because it: (i) has fewest parameters; (ii) is most robust in practice, and (iii) can be optimized well with an efficient EM-style procedure.

Graph cut is a popular technique for interactive image segmentation. However, it has certain shortcomings. In particular, graph cut has problems with segmenting thin elongated objects due to the ldquoshrinking biasrdquo. To overcome this problem, we propose to impose an additional connectivity prior, which is a very natural assumption about objects. We formulate several versions of the connectivity constraint and show that the corresponding optimization problems are all NP-hard. For some of these versions we propose two optimization algorithms: (i) a practical heuristic technique which we call DijkstraGC, and (ii) a slow method based on problem decomposition which provides a lower bound on the problem. We use the second technique to verify that for some practical examples DijkstraGC is able to find the global minimum.